GOTO Copenhagen 2022

Thursday Oct 6
09:00 –
Friday Oct 7
09:00 –

2 Days: Machine Learning - get value out of your data

In this course you’ll be introduced to the concepts and applications of Machine Learning. You will learn various supervised and unsupervised ML algorithms and prediction tasks applied to different data. Moreover, by taking this course you’ll be able to understand how to choose the right model for your data.


  • Basic coding or scripting knowledge is required.

After this course you will be able to:

  • Recognize different business problems that could be addressed using the potential of machine learning and artificial intelligence.
  • Identify when to use machine learning to explain certain behaviors and when to use it to predict future outcomes.
  • Understand how machine learning can be applied to numerical, text and image data.
  • Clean and prepare data, perform Exploratory Data Analysis (EDA) and train classification model
  • Identify the differences between some of the most popular machine learning models.
  • Evaluate how good a your machine learning model is and how to incorporate best practices.

The two-day course will be instructor led with hands-on exercises. The focus will be on giving the participants the knowledge and the confidence to apply machine learning to problems that they face in their own work. The course will touch upon many aspects of machine learning, but emphasis will be on classification tasks.

Participants are expected to bring own laptop to the class, everything else needed for course is provided.

The hands-on exercises will be browser-based, so there is no need to install software, but participants should either have or be willing to sign-up for a free Google account.


Day 1 09:00-16:00

  • Introduction to Machine Learning
  • Supervised VS Unsupervised Learning
  • Data preparation
  • Classification
  • Regression
  • Overfitting
  • Python, NumPy, Tensorflow
  • Multilayer perceptron

Day 2 09:00-16:00

  • Working with natural language
  • Bag of words
  • Deep Learning
  • Image recognition
  • Training Neural networks
  • Tips and tricks on how to come forward from here
Powered by